Gaussian function
PulseAugur coverage of Gaussian function — every cluster mentioning Gaussian function across labs, papers, and developer communities, ranked by signal.
- used by Bayesian Neural Networks 80%
- used by Laplace 70%
- instance of Poisson 70%
- used by Monte Carlo 70%
- instance of Laplace 70%
- used by optimal transport 70%
- instance of optimal transport 70%
- used by Poisson 70%
- used by Student's t-test 70%
- used by Gotit.pub 60%
- used by ScienceCast 60%
- used by alphaXiv 60%
17 day(s) with sentiment data
-
New learning procedure achieves universal sample complexity bounds
Researchers have developed a new learning procedure that can achieve state-of-the-art sample complexity bounds in convex learning problems, even in heavy-tailed scenarios. This method utilizes optimal mean estimation te…
-
New AdaptivePnP method automates image reconstruction parameter tuning
Researchers have developed AdaptivePnP, a novel framework for image reconstruction that automatically tunes key parameters, eliminating the need for manual adjustments. This method jointly estimates the measurement nois…
-
New Bayesian Method Enhances Deep Learning Model Confidence
A new research paper proposes a novel approach to improve the confidence calibration of deep learning models by introducing a degenerate Gaussian distribution on parameter space. This method aims to bridge the gap betwe…
-
New Onsager Correction Method Improves High-Dimensional Off-Policy Evaluation
Researchers have developed a new method for off-policy evaluation (OPE) in high-dimensional settings that avoids sample splitting. This Onsager-corrected criterion estimates the out-of-sample risk of reward models using…
-
SplatAnything advances 3D Gaussian Splatting with novel normalization technique
Researchers have introduced SplatAnything, a novel method that enhances feed-forward 3D Gaussian Splatting (3DGS) by normalizing Gaussian spacing statistics. This approach addresses a key limitation in existing 3DGS tec…
-
DISCERN method enhances incremental machine unlearning for transformers
Researchers have developed DISCERN, a novel method for incremental machine unlearning that addresses the challenge of sequentially removing data classes from a trained model while preserving remaining knowledge. DISCERN…
-
New research details fundamental limits of coherent imaging under atmospheric turbulence
This paper explores the theoretical limits of coherent imaging when dealing with atmospheric turbulence. Researchers analyzed a maximum likelihood estimator to establish an upper bound on the minimax risk, considering f…
-
Kernel-Based Hypothesis Testing Explores Regularization vs. Convolution
This paper explores kernel-based hypothesis testing, specifically focusing on the Maximum Mean Discrepancy (MMD) test. It investigates two distinct approaches: a convolution method for translation-invariant kernels on $…
-
ESS-Flow method enables training-free guidance for generative models
Researchers have introduced ESS-Flow, a novel method for guiding pretrained flow-based generative models without requiring retraining. This technique utilizes Bayesian inference in the source space via elliptical slice …
-
New CANDO RL method enhances robot control by adapting generative policies
Researchers have developed Conservative Action-Noise Directional Optimization (CANDO), a novel reinforcement learning method designed to efficiently adapt pretrained generative policies for robot control. CANDO improves…
-
New research details gradient descent dynamics in simplified neural networks
A new paper published on arXiv details the complex dynamics of gradient descent in a simplified neural network model. Researchers analyzed a two-neuron Rectified Linear Unit (ReLU) network trained with gradient flow, re…
-
New method optimizes privacy spending in machine learning training
Researchers have developed a new method for optimizing privacy allocation in machine learning, specifically for Differentially Private Stochastic Gradient Descent (DPSGD). The approach formulates the Gaussian noise-vari…
-
New AI models improve CBCT image reconstruction from sparse data · 2 sources tracked
Two new research papers introduce advanced methods for reconstructing cone-beam computed tomography (CBCT) images from sparse projection data. EUReCA, a geometry-aware feed-forward model, integrates learned projection f…
-
New research examines statistical efficiency in denoising score matching
A new research paper explores the statistical efficiency of denoising score matching, a technique used in machine learning for approximating probability distributions. The study focuses on finite-dimensional approximati…
-
New diffusion framework unifies Gaussian, Poisson, and Gamma noise models
Researchers have introduced p-Bridge, a novel diffusion framework designed to handle various types of sensor noise beyond the common Gaussian model. This unified approach accounts for noise characteristics defined by an…
-
New Random-Bridges Framework Enhances Generative Models
Researchers have introduced a novel framework called Random-Bridges, which utilizes stochastic processes to act as transports between probability distributions for generative modeling. This approach can generate high-qu…
-
New framework certifies ML model robustness against backdoor poisoning attacks
Researchers have developed a new framework for certifying the robustness of machine learning models against backdoor poisoning attacks. This framework utilizes $f$-divergences to handle complex adversary constraints, in…
-
New Rènyi Regularization Tackles Mode Collapse in Bayesian Inference
Researchers have developed a new method called Rènyi-Regularized Flow-Based Variational Inference to address mode collapse in Bayesian model calibration. This technique aims to improve posterior approximation by introdu…
-
New TOPS method enhances multi-task robot manipulation with adaptive priors
Researchers have developed TOPS (Task-Oriented Priors and Schedules), a novel method for language-conditioned multi-task robot manipulation. TOPS adapts the flow source prior and interpolation schedule to individual tas…
-
New AutoPRL framework enhances path representation learning for road networks
Researchers have introduced AutoPRL, a novel self-supervised learning framework designed to enhance Path Representation Learning (PRL) in road networks. This framework addresses limitations in existing methods by employ…